Metric free nearness measure using description-based neighbourhoods

Abstract

The focus of this paper is on a metric free nearness measure for quantifying the descriptive nearness of digital images. Regions of Interest (ROI) play an important role in discerning perceptual similarity within a single image, or between a pair of images. In terms of pixels, closeness between ROIs can be assessed in light of the traditional closeness between points and sets and closeness between sets using topology or proximity theory. A metric free nearness measure is introduced in this paper by finding common patterns among disjoint description based neighbourhoods obtained from these spatially defined sets. The contribution of this article is a metric free nearness measure implemented within the Proximity System, an application used to demonstrate near set concepts using digital images.